Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2151 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9380. Min Range: -0.9380

Max Act: 0.9380. Min Act: -0.0001

Data Index: 14085 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.9380. Min Range: -0.9380

Max Act: 0.8316. Min Act: -0.0001

Data Index: 384136 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.9380. Min Range: -0.9380

Max Act: 0.7023. Min Act: -0.0001

Data Index: 574722 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.9380. Min Range: -0.9380

Max Act: 0.6772. Min Act: -0.0001

Data Index: 1355489 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.9380. Min Range: -0.9380

Max Act: 0.5603. Min Act: -0.0001

Data Index: 186962 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.9380. Min Range: -0.9380

Max Act: 0.5873. Min Act: -0.0001

Data Index: 487687 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.9380. Min Range: -0.9380

Max Act: 0.5700. Min Act: -0.0001

Data Index: 259757 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.9380. Min Range: -0.9380

Max Act: 0.5566. Min Act: -0.0001

Data Index: 415584 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 0.9380. Min Range: -0.9380

Max Act: 0.5345. Min Act: -0.0001

Data Index: 964192 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.9380. Min Range: -0.9380

Max Act: 0.5510. Min Act: -0.0001

Data Index: 8808 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.9380. Min Range: -0.9380

Max Act: 0.5656. Min Act: -0.0001

Data Index: 976299 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.9380. Min Range: -0.9380

Max Act: 0.5213. Min Act: -0.0001

Data Index: 671448 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.9380. Min Range: -0.9380

Max Act: 0.5271. Min Act: -0.0001

Data Index: 409907 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.9380. Min Range: -0.9380

Max Act: 0.6068. Min Act: -0.0001

Data Index: 343464 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.9380. Min Range: -0.9380

Max Act: 0.5260. Min Act: -0.0001

Data Index: 824655 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.9380. Min Range: -0.9380

Max Act: 0.5068. Min Act: -0.0001

Data Index: 780744 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 0.9380. Min Range: -0.9380

Max Act: 0.5607. Min Act: -0.0001

Data Index: 1026702 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.9380. Min Range: -0.9380

Max Act: 0.5193. Min Act: -0.0001

Data Index: 271306 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.9380. Min Range: -0.9380

Max Act: 0.4598. Min Act: -0.0001

Data Index: 442581 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.9380. Min Range: -0.9380

Max Act: 0.4881. Min Act: -0.0001

Data Index: 1298807 (C4 (Web Text))

Max Activating Token Index: 75